#### Filter Results:

- Full text PDF available (25)

#### Publication Year

2007

2017

- This year (0)
- Last 5 years (14)
- Last 10 years (27)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

We study the learnability of linear separators in < in the presence of bounded (a.k.a Massart) noise. This is a realistic generalization of the random classification noise model, where the adversary… (More)

- Ruth Urner, Sharon Wulff, Shai Ben-David
- COLT
- 2013

We investigate the label complexity of active learning under some smoothness assumptions on the data-generating process. We propose a procedure, PLAL, for “activising” passive, sample-based learners.… (More)

- Shai Ben-David, Ruth Urner
- ALT
- 2012

The Domain Adaptation problem in machine learning occurs when the test and training data generating distributions differ. We consider the covariate shift setting, where the labeling function is the… (More)

- Sharon Wulff, Ruth Urner, Shai Ben-David
- ICML
- 2013

We propose a natural cost function for the bi-clustering task, the monochromatic cost. This cost function is suitable for detecting meaningful homogeneous bi-clusters based on categorical valued… (More)

- Shai Ben-David, Shai Shalev-Shwartz, Ruth Urner
- Annals of Mathematics and Artificial Intelligence
- 2012

The Domain Adaptation problem in machine learning occurs when the distribution generating the test data differs from the one that generates the training data. A common approach to this issue is to… (More)

- Ruth Urner, Shai Ben-David, Ohad Shamir
- AISTATS
- 2012

This paper addresses the problem of learning when high-quality labeled examples are an expensive resource, while samples with error-prone labeling (for example generated by crowdsourcing) are readily… (More)

We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems. In MIL a learner receives training instances grouped together into bags… (More)

- Ruth Urner
- 2013

We present Probabilistic Lipschitzness (PL), a notion of marginal label relatedness that is particularly useful for modeling niceness of distributions with deterministic labeling functions. We… (More)

A recent line of work, starting with Beigman and Vohra [3] and Zadimoghaddam and Roth [28], has addressed the problem of learning a utility function from revealed preference data. The goal here is to… (More)

- Ruth Urner, Shai Shalev-Shwartz, Shai Ben-David
- ICML
- 2011

Semi-supervised learning (SSL) addresses the problem of training a classifier using a small number of labeled examples and many unlabeled examples. Most previous work on SSL focused on how… (More)